mirror of
https://github.com/catlog22/Claude-Code-Workflow.git
synced 2026-02-11 02:33:51 +08:00
487b359266
Core Changes (10 files): - commands: cli/execute.md, memory/docs.md, workflow/review.md, workflow/brainstorm/*.md - agents: cli-execution-agent.md - workflows: task-core.md, workflow-architecture.md Transformations: - Removed all .active-* marker file operations (touch/rm/find) - Updated session discovery to directory-based (.workflow/sessions/) - Updated directory structure examples to show sessions/ subdirectory - Replaced marker-based state with location-based state Reference Documentation (57 files): - Auto-synced via analyze_commands.py script - Includes all core file changes - Updated command indexes (all-commands.json, by-category.json, etc.) Migration complete: 100% .active marker references removed Session state now determined by directory location only
2.9 KiB
2.9 KiB
name, description, argument-hint
| name | description | argument-hint |
|---|---|---|
| enhance-prompt | Enhanced prompt transformation using session memory and intent analysis with --enhance flag detection | user input to enhance |
Overview
Systematically enhances user prompts by leveraging session memory context and intent analysis, translating ambiguous requests into actionable specifications.
Core Protocol
Enhancement Pipeline:
Intent Translation → Context Integration → Structured Output
Context Sources:
- Session memory (conversation history, previous analysis)
- Implicit technical requirements
- User intent patterns
Enhancement Rules
Intent Translation
| User Says | Translate To | Focus |
|---|---|---|
| "fix" | Debug and resolve | Root cause → preserve behavior |
| "improve" | Enhance/optimize | Performance/readability |
| "add" | Implement feature | Integration + edge cases |
| "refactor" | Restructure quality | Maintain behavior |
| "update" | Modernize | Version compatibility |
Context Integration Strategy
Session Memory:
- Reference recent conversation context
- Reuse previously identified patterns
- Build on established understanding
- Infer technical requirements from discussion
Example:
# User: "add login"
# Session Memory: Previous auth discussion, JWT mentioned
# Inferred: JWT-based auth, integrate with existing session management
# Action: Implement JWT authentication with session persistence
Output Structure
INTENT: [Clear technical goal]
CONTEXT: [Session memory + codebase patterns]
ACTION: [Specific implementation steps]
ATTENTION: [Critical constraints]
Output Examples
Example 1:
# Input: "fix login button"
INTENT: Debug non-functional login button
CONTEXT: From session - OAuth flow discussed, known state issue
ACTION: Check event binding → verify state updates → test auth flow
ATTENTION: Preserve existing OAuth integration
Example 2:
# Input: "refactor payment code"
INTENT: Restructure payment module for maintainability
CONTEXT: Session memory - PCI compliance requirements, Stripe integration patterns
ACTION: Extract reusable validators → isolate payment gateway logic → maintain adapter pattern
ATTENTION: Zero behavior change, maintain PCI compliance, full test coverage
Enhancement Triggers
- Ambiguous language: "fix", "improve", "clean up"
- Vague requests requiring clarification
- Complex technical requirements
- Architecture changes
- Critical systems: auth, payment, security
- Multi-step refactoring
Key Principles
- Session Memory First: Leverage conversation context and established understanding
- Context Reuse: Build on previous discussions and decisions
- Clear Output: Structured, actionable specifications
- Intent Clarification: Transform vague requests into specific technical goals
- Avoid Duplication: Reference existing context, don't repeat